Update app.py

app.py

@@ -23,22 +23,19 @@ canny_model = create_model('./models/cldm_v15.yaml')
 canny_model.load_state_dict(load_state_dict(cached_download(
     hf_hub_url(REPO_ID, canny_checkpoint)
 ), location='cpu'))
-ddim_sampler_canny = DDIMSampler(canny_model)
+ddim_sampler = DDIMSampler(canny_model)
 
 
-pose_model = create_model('./models/cldm_v15.yaml')
-pose_model.load_state_dict(load_state_dict(cached_download(
-    hf_hub_url(REPO_ID, pose_checkpoint)
-), location='cpu'))
-ddim_sampler_pose = DDIMSampler(pose_model)
+# pose_model = create_model('./models/cldm_v15.yaml')
+# pose_model.load_state_dict(load_state_dict(cached_download(
+#     hf_hub_url(REPO_ID, pose_checkpoint)
+# ), location='cpu'))
+# ddim_sampler_pose = DDIMSampler(pose_model)
 
 def process(input_image, prompt, input_control, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold):
     # TODO: Add other control tasks
-    if input_control == "Canny Edge Map":
-        return process_canny(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold)
-    else:
-        return process_pose(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta)
-
+    return process_canny(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold)
+    
 def process_canny(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold):
     with torch.no_grad():
         img = resize_image(HWC3(input_image), image_resolution)
@@ -67,40 +64,11 @@ def process_canny(input_image, prompt, a_prompt, n_prompt, num_samples, image_re
         results = [x_samples[i] for i in range(num_samples)]
     return [255 - detected_map] + results
 
-def process_pose(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta):
-    with torch.no_grad():
-        input_image = HWC3(input_image)
-        detected_map, _ = apply_openpose(resize_image(input_image, image_resolution))
-        detected_map = HWC3(detected_map)
-        img = resize_image(input_image, image_resolution)
-        H, W, C = img.shape
-
-        detected_map = cv2.resize(detected_map, (W, H), interpolation=cv2.INTER_NEAREST)
-
-        control = torch.from_numpy(detected_map.copy()).float() / 255.0
-        control = torch.stack([control for _ in range(num_samples)], dim=0)
-        control = einops.rearrange(control, 'b h w c -> b c h w').clone()
 
-        seed_everything(seed)
-
-        cond = {"c_concat": [control], "c_crossattn": [pose_model.get_learned_conditioning([prompt + ', ' + a_prompt] * num_samples)]}
-        un_cond = {"c_concat": [control], "c_crossattn": [pose_model.get_learned_conditioning([n_prompt] * num_samples)]}
-        shape = (4, H // 8, W // 8)
-
-        samples, intermediates = ddim_sampler_pose.sample(ddim_steps, num_samples,
-                                                     shape, cond, verbose=False, eta=eta,
-                                                     unconditional_guidance_scale=scale,
-                                                     unconditional_conditioning=un_cond)
-        x_samples = pose_model.decode_first_stage(samples)
-        x_samples = (einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 + 127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
-
-        results = [x_samples[i] for i in range(num_samples)]
-    return [detected_map] + results
     
 block = gr.Blocks().queue()
 control_task_list = [
-    "Canny Edge Map",
-    "Human Pose"
+    "Canny Edge Map"
 ]
 with block:
     gr.Markdown("## Adding Conditional Control to Text-to-Image Diffusion Models")